A study of Bayesian local robustness with applications in actuarial statistics

Local or infinitesimal Bayesian robustness is a powerful tool to study the sensitivity of posterior magnitudes, which cannot be expressed in a simple manner. For these expressions, the global Bayesian robustness methodology does not seem adequate since the practitioner cannot avoid using inappropriate classes of prior distributions in order to make the model mathematically tractable. This situation occurs, for example, when we compute some types of premiums in actuarial statistics in order to fix the premium to be charged to an insurance policy. In this paper, analytical and simple expressions that allow us to study the sensitivity of premiums, which are usually used in automobile insurance are provided by using the local Bayesian robustness methodology. Some examples are examined by using real automobile claim insurance data.     

A comparison of risk transfer strategies for a portfolio of life annuities based on RORAC

This paper aims to compare different reinsurance arrangements in order to reduce the longevity and financial risk originated by a life insurer while managing a portfolio of annuities policies. Linear and nonlinear reinsurance strategies as well as swap like agreements are evaluated via a discrete-time actuarial risk model. Specifically, longevity dynamics are represented by Lee–Carter type models, while interest rate is modeled by Cox–Ingersoll–Ross model. The reinsurance strategies effectiveness is evaluated according to the Return on Risk Adjusted Capital under a ruin probability constrain.     

Industrial applications of cross-impact analysis

The implicit or explicit ceteris paribus assumption usually made in the planning of economic systems (e.g. industries) is acceptable and accepted during periods of regular economic development; in this context, sensitivity analysis around the central projection is often used in order to measure effective elasticities to unexpected small perturbations of the system.In periods of structural change, unpredictable major events greatly reduce the value of any trend projection, and the ceteris paribus assumption has to be replaced by ‘scenarios’ of the future environment.The causal structure which generates these events is unknown; in such a situation, it seems reasonable to rely upon ‘opinions’ in order to assess the a priori probabilities of these events. Cross-impact analysis is one of the methods developed in order to improve human probability judgments of single and pairs of events and in order to deal explicitly with higher order interactions; in particular, cross-impact allows for the computation of the most probable combination of the events considered, or ‘most probable scenario’. In the industrial planning process, this ‘most probable scenario’ can be used as the set of exogeneous conditions for the central projection.     

Transparency in the European Bond Market

The European bond market is made up of many segments characterised by varying levels of liquidity and of pre- and post-trade transparency. The possibility of extending the transparency provisions envisioned in the Directive 2004/39/EC, disciplining the functioning of markets in financial instruments in Europe (MiFID), from the equity to the bond market is currently being discussed. This poses risks to the status quo through trading fragmentation and strong negotiating power of a few large dealers, particularly with respect to small retail investors. The main conclusion of the paper is that if MiFID transparency rules are to be extended to the bond market, this must be “real” transparency, meaning pre-trade dissemination of real-time executable prices and a transparent order book. Under current provisions, this kind of information is available if not directly to everybody, at least directly to dealers and indirectly to professional and retail clients through business-to-business electronic platforms.     

Are people in the South less intelligent than in the North? IQ and the North–South disparity in Italy

Socioeconomic disparity between North and South Italy has been recently explained by Lynn (2010) as the result of a lower intelligence quotient (IQ) of the Southern population. The present article discusses the procedure followed by Lynn, supplementing his data with new information on school assessments and per head regional income. Genetic North–South differences are then discussed on the basis of the most recent literature on the subject. The results do not confirm the suggested IQ-economy causal link.     

Monte Carlo methods for nonparametric survival model determination

In the causal analysis of survival data a time-based response is related to a set of explanatory variables. Definition of the relation between the time and the covariates may become a difficult task, particularly in the preliminary stage, when the information is limited. Through a nonparametric approach, we propose to estimate the survival function allowing to evaluate the relative importance of each potential explanatory variable, in a simple and explanatory fashion. To achieve this aim, each of the explanatory variables is used to partition the observed survival times. The observations are assumed to be partially exchangeable according to such partition. We then consider, conditionally on each partition, a hierarchical nonparametric Bayesian model on the hazard functions. We define and compare different prior distribution for the hazard functions.     

Protest avatars as memetic signifiers: political profile pictures and the construction of collective identity on social media in the 2011 protest wave

Protest avatars, digital images that act as collective symbols for protest movements, have been widely used by supporters of the 2011 protest wave, from Egypt to Spain and the United States. From photos of Egyptian martyr Khaled Said, to protest posters and multiple variations of Anonymous' mask, a great variety of images have been adopted as profile pictures by Internet users to express their support for various causes and protest movements and communicate it to all their Internet peers. In this article, I explore protest avatars as forms of identification of protest movements in a digital era. I argue that protest avatars can be described as ‘memetic signifiers’ because (a) they are marked by a vagueness and inclusivity that distinguishes them from traditional protest symbols and (b) lend themselves to be used as memes for viral diffusion on social networks. In adopting these icons, participants experience a collective fusion in an online crowd, whose gathering is manifested in the very ‘masking’ of participants behind protest avatars. These forms of collective identification, while powerful in the short term, can however prove quite volatile, with Internet users often discarding avatars with relative ease, raising the question whether they can provide durable foundational elements of contemporary social movements.